Cov-Pneum

We prepared a new dataset (Cov-Pneum) for X-ray images by processing and merging three well-known publicly available datasets from Kaggle [1]–[4]. This dataset includes a total of 21,272 CXR images of COVID-19 (COVID-19 virus-infected lung), pneumonia (pneumonia-infected lung), and normal (clear lung) and consisting of images 4296, 5824, and 11152, respectively. We applied image scaling and preprocessing operations to enhance the quality of these CXR images.

[1] M. E. Chowdhury, T. Rahman, A. Khandakar, R. Mazhar, M. A. Kadir, Z. B. Mahbub, K. R. Islam, M. S. Khan, A. Iqbal, N. Al Emadi et al., “Can ai help in screening viral and covid-19 pneumonia?” IEEE Access, vol. 8, pp. 132 665–132 676, 2020.

[2] T. Rahman, A. Khandakar, Y. Qiblawey, A. Tahir, S. Kiranyaz, S. B. A. Kashem, M. T. Islam, S. Al Maadeed, S. M. Zughaier, M. S. Khan et al., “Exploring the effect of image enhancement techniques on covid-19 detection using chest x-ray images,” Computers in biology and medicine, vol. 132, p. 104319, 2021.

[3] Kaggle, “Chest x-ray images (pneumonia),” 2021. [Online]. Available: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia

[4] ——, “Covid-net open source initiative - covidx cxr-3 dataset,” 2021. [Online]. Available: https://www.kaggle.com/andyczhao/COVIDx-cxr2?select= test